© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 18434
    Prev
    Next
    INDEX
    Explanations

    camel

    np_max-act · gemini-2.0-flash

    elements related to programming conventions and naming strategies in code, particularly focusing on camel case and underscores.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    their
    -0.06
    ­i
    -0.06
    	headers
    -0.06
     Technician
    -0.06
     Bans
    -0.06
     *__
    -0.06
     implants
    -0.06
     illum
    -0.06
    operands
    -0.06
    Combine
    -0.06
    POSITIVE LOGITS
    Interface
    0.07
     slaughter
    0.07
    _navigation
    0.07
     caused
    0.07
    -trigger
    0.07
    些
    0.06
    aff
    0.06
    .Normal
    0.06
     навер
    0.06
     incontr
    0.06
    Activations Density 0.009%

    No Known Activations